Araştırma Makalesi

Enhancing Long-Tail Exposure in Session-Based Recommendation via Tail-Aware Training

Cilt: 13 Sayı: 1 2 Ekim 2026
Ramazan Eşmeli *
PDF İndir
Adıyaman Üniversitesi Mühendislik Bilimleri Dergisi Kapak Adıyaman Üniversitesi Mühendislik Bilimleri Dergisi
EN TR

Enhancing Long-Tail Exposure in Session-Based Recommendation via Tail-Aware Training

Öz

Recommender systems often concentrate exposure on popular items, limiting catalogue utilization and leaving long-tail items underexposed. This study evaluates TAILPromote under a leakage-controlled temporal protocol in which all eligibility, vocabulary, popularity, and long-tail definitions are derived from training data alone. TAILPromote combines a SASRec backbone with a gated tail-specific residual expert, popularity-aware logit adjustment, and catalogue-coverage regularization. Across five seeds on YooChoose 1/64, it attains MRR@20 of 33.04% ± 0.12, Coverage@20 of 89.93% ± 0.42, and LTP@20 of 39.63% ± 0.51. Paired hierarchical-bootstrap tests with Holm correction show lower accuracy than NISER+ but higher accuracy than SASRec and TailNet, together with significantly greater long-tail exposure than all three baselines. Factorial analyses identify logit adjustment as the main exposure contributor, with a smaller significant effect from Tail Expert gating. These results show that TAILPromote provides a controllable accuracy–exposure trade-off. Further evaluation on additional datasets and online settings is needed to assess generalizability and user-level utility.

Anahtar Kelimeler

Long-tail Item Coverage, Popularity Bias, Accuracy-Diversity Trade-off

Kaynakça

  1. Pan LW, Pan WK, Wei MY, Yin HZ, Ming Z. A survey on sequential recommendation. Frontiers of Computer Science 2026;20(3):2003606. https://doi.org/10.1007/s11704-025-41329-w
  2. Esmeli R, Can AS, Awad A, Bader-El-Den M. Understanding customer loyalty-aware recommender systems in E-commerce: an analytical perspective. Electronic Commerce Research 2025:1–27. https://doi.org/10.1007/s10660-025-09954-6
  3. Klimashevskaia A, Jannach D, Elahi M, Trattner C. A survey on popularity bias in recommender systems. User Modeling and User-Adapted Interaction 2024;34(5):1777–1834. https://doi.org/10.1007/s11257-024-09406-0
  4. Carnovalini F, Rodà A, Wiggins GA. Popularity Bias in Recommender Systems: The Search for Fairness in the Long Tail. Information 2025;16(2):151. https://doi.org/10.3390/info16020151
  5. Park YJ, Tuzhilin A. The long tail of recommender systems and how to leverage it. In: Proceedings of the 2008 ACM conference on Recommender systems; 2008. p. 11–18. https://doi.org/10.1145/1454008.1454012
  6. Yu D, Yu T, Wang D, Wang S. Long tail service recommendation based on cross-view and contrastive learning. Expert Systems with Applications 2024;238:121957. https://doi.org/10.1016/j.eswa.2023.121957
  7. De Campos LM, Fernández Luna JM, Huete Guadix JF. An explainable content-based approach for recommender systems: a case study in journal recommendation for paper submission. User Modeling and User-Adapted Interaction 2024. https://doi.org/10.1007/s11257-024-09400-6
  8. Kumar C, Kumar M. Session-based recommendations with sequential context using attention-driven LSTM. Computers and Electrical Engineering 2024;115:109138. https://doi.org/10.1016/j.compeleceng.2024.109138
  9. Peng D, Zhou Y. A long-tail alleviation post-processing framework based on personalized diversity of session recommendation. Expert Systems with Applications 2024;249:123769. https://doi.org/10.1016/j.eswa.2024.123769
  10. Liu S, Zheng Y. Long-tail session-based recommendation. In: Proceedings of the 14th ACM conference on recommender systems; 2020. p. 509–514. https://doi.org/10.1145/3383313.3412222

Ayrıntılar

Birincil Dil

İngilizce

Konular

Makine Öğrenmesi Algoritmaları

Bölüm

Araştırma Makalesi

Yazarlar

Yayımlanma Tarihi

2 Ekim 2026

Gönderilme Tarihi

3 Mart 2026

Kabul Tarihi

27 Ağustos 2026

Yayımlandığı Sayı

Yıl 2026 Cilt: 13 Sayı: 1

DOI

https://doi.org/10.54365/adyumbd.1901974

IZ

https://izlik.org/JA86LS54JZ

Kaynak Göster

RIS / Bibtex
APA
Eşmeli, R. (2026). Enhancing Long-Tail Exposure in Session-Based Recommendation via Tail-Aware Training. Adıyaman Üniversitesi Mühendislik Bilimleri Dergisi, 13(1), 1-25. https://doi.org/10.54365/adyumbd.1901974
AMA
1.Eşmeli R. Enhancing Long-Tail Exposure in Session-Based Recommendation via Tail-Aware Training. Adıyaman Üniversitesi Mühendislik Bilimleri Dergisi. 2026;13(1):1-25. doi:10.54365/adyumbd.1901974
Chicago
Eşmeli, Ramazan. 2026. “Enhancing Long-Tail Exposure in Session-Based Recommendation via Tail-Aware Training”. Adıyaman Üniversitesi Mühendislik Bilimleri Dergisi 13 (1): 1-25. https://doi.org/10.54365/adyumbd.1901974.
EndNote
Eşmeli R (01 Ekim 2026) Enhancing Long-Tail Exposure in Session-Based Recommendation via Tail-Aware Training. Adıyaman Üniversitesi Mühendislik Bilimleri Dergisi 13 1 1–25.
IEEE
[1]R. Eşmeli, “Enhancing Long-Tail Exposure in Session-Based Recommendation via Tail-Aware Training”, Adıyaman Üniversitesi Mühendislik Bilimleri Dergisi, c. 13, sy 1, ss. 1–25, Eki. 2026, doi: 10.54365/adyumbd.1901974.
ISNAD
Eşmeli, Ramazan. “Enhancing Long-Tail Exposure in Session-Based Recommendation via Tail-Aware Training”. Adıyaman Üniversitesi Mühendislik Bilimleri Dergisi 13/1 (01 Ekim 2026): 1-25. https://doi.org/10.54365/adyumbd.1901974.
JAMA
1.Eşmeli R. Enhancing Long-Tail Exposure in Session-Based Recommendation via Tail-Aware Training. Adıyaman Üniversitesi Mühendislik Bilimleri Dergisi. 2026;13:1–25.
MLA
Eşmeli, Ramazan. “Enhancing Long-Tail Exposure in Session-Based Recommendation via Tail-Aware Training”. Adıyaman Üniversitesi Mühendislik Bilimleri Dergisi, c. 13, sy 1, Ekim 2026, ss. 1-25, doi:10.54365/adyumbd.1901974.
Vancouver
1.Ramazan Eşmeli. Enhancing Long-Tail Exposure in Session-Based Recommendation via Tail-Aware Training. Adıyaman Üniversitesi Mühendislik Bilimleri Dergisi. 01 Ekim 2026;13(1):1-25. doi:10.54365/adyumbd.1901974